Cardiovascular risk assessment is a basic tenet of the prevention of cardiovascular disease. Conventional risk assessment models require measurements of blood pressure, blood lipids, and other health-related information prior to assessment of risk via regression models. Compared with traditional approaches, fundus photograph-based cardiovascular risk assessment using artificial intelligence (AI) technology is novel, and has the advantages of immediacy, non-invasiveness, easy performance, and low cost. The Health Risk Assessment and Control Committee of the Chinese Preventive Medicine Association, in collaboration with the Chinese Society of Cardiology and the Society of Health Examination, invited multi-disciplinary experts to form a panel to develop the present consensus, which includes relevant theories, progress in research, and requirements for AI model development, as well as applicable scenarios, applicable subjects, assessment processes, and other issues associated with applying AI technology to assess cardiovascular risk based on fundus photographs. A consensus was reached after multiple careful discussions on the relevant research, and the needs of the health management industry in China and abroad, in order to guide the development and promotion of this new technology.
Humans ; Cardiovascular Diseases/prevention & control* ; Artificial Intelligence ; Consensus ; Risk Factors ; Heart Disease Risk Factors

Objective: To explore the indications and management of common postoperative complications of phase II tracheoesophageal puncture (TEP) for Provox Vega voice prosthesis after total laryngectomy. Methods: The clinical data of 20 patients undergoing phase II TEP for Provox Vega voice prosthesis in our hospital between May 2021 and January 2022 were analyzed. Among them, there were 19 males and 1 female, aged from 37 to 76 years, with an average age of (60.0±8.4)years. The surgical indications and the prevention and treatment of common postoperative complications were summarized. Descriptive analysis was used in this research. Results: The basic surgical indications were as following: after total laryngectomy, there was no stenosis of the stoma and esophagus entrance, no scar constitution, no mouth opening restriction, no stiffness and backward restraint of the neck after radiotherapy, and more than half a year apart surgery or radiotherapy. Among the 20 patients, 18 underwent implantation successfuly, 1 failed in the operation, and for 1 patient, the prosthesis was removed due to bleeding 1 week after implantation. The common postoperative complications included TEP fistula infection (2 cases), the TEP fistula bleeding(1 case), deep neck (prevertebral) abscess (1 case), granulation at the inner side of the TEP fistula (1 case), invagination of the prosthesis (2 cases) and leakage around the prosthesis (2 cases). All patients were cured with different interventions. Conclusions: The Provox Vega voice prosthesis is generally safe for phase Ⅱ implantatione, but implantation indications need to be established. Common postoperative complications can be solved through preventive and remedial interventions.
Male ; Humans ; Female ; Larynx, Artificial/adverse effects* ; Laryngectomy/adverse effects* ; Prosthesis Implantation/adverse effects* ; Esophagus/surgery* ; Postoperative Complications/etiology* ; Prosthesis Design

Heart failure is a disease that seriously threatens human health and has become a global public health problem. Diagnostic and prognostic analysis of heart failure based on medical imaging and clinical data can reveal the progression of heart failure and reduce the risk of death of patients, which has important research value. The traditional analysis methods based on statistics and machine learning have some problems, such as insufficient model capability, poor accuracy due to prior dependence, and poor model adaptability. In recent years, with the development of artificial intelligence technology, deep learning has been gradually applied to clinical data analysis in the field of heart failure, showing a new perspective. This paper reviews the main progress, application methods and major achievements of deep learning in heart failure diagnosis, heart failure mortality and heart failure readmission, summarizes the existing problems and presents the prospects of related research to promote the clinical application of deep learning in heart failure clinical research.
Humans ; Artificial Intelligence ; Deep Learning ; Heart Failure/diagnosis* ; Machine Learning ; Diagnostic Imaging

OBJECTIVE: To design customized titanium alloy lunate prosthesis, construct three-dimensional finite element model of wrist joint before and after replacement by finite element analysis, and observe the biomechanical changes of wrist joint after replacement, providing biomechanical basis for clinical application of prosthesis. METHODS: One fresh frozen human forearm was collected, and the maximum range of motions in flexion, extension, ulnar deviation, and radialis deviation tested by cortex motion capture system were 48.42°, 38.04°, 35.68°, and 26.41°, respectively. The wrist joint data was obtained by CT scan and imported into Mimics21.0 software and Magics21.0 software to construct a wrist joint three-dimensional model and design customized titanium alloy lunate prosthesis. Then Geomagic Studio 2017 software and Solidworks 2017 software were used to construct the three-dimensional finite element models of a normal wrist joint (normal model) and a wrist joint with lunate prosthesis after replacement (replacement model). The stress distribution and deformation of the wrist joint before and after replacement were analyzed for flexion at and 15°, 30°, 48.42°, extension at 15°, 30°, and 38.04°, ulnar deviation at 10°, 20°, and 35.68°, and radial deviation at 5°, 15°, and 26.41° by the ANSYS 17.0 finite element analysis software. And the stress distribution of lunate bone and lunate prosthesis were also observed. RESULTS: The three-dimensional finite element models of wrist joint before and after replacement were successfully constructed. At different range of motion of flexion, extension, ulnar deviation, and radial deviation, there were some differences in the number of nodes and units in the grid models. In the four directions of flexion, extension, ulnar deviation, and radial deviation, the maximum deformation of wrist joint in normal model and replacement model occurred in the radial side, and the values increased gradually with the increase of the range of motion. The maximum stress of the wrist joint increased gradually with the increase of the range of motion, and at maximum range of motion, the stress was concentrated on the proximal radius, showing an overall trend of moving from the radial wrist to the proximal radius. The maximum stress of normal lunate bone increased gradually with the increase of range of motion in different directions, and the stress position also changed. The maximum stress of lunate prosthesis was concentrated on the ulnar side of the prosthesis, which increased gradually with the increase of the range of motion in flexion, and decreased gradually with the increase of the range of motion in extension, ulnar deviation, and radialis deviation. The stress on prosthesis increased significantly when compared with that on normal lunate bone. CONCLUSION The customized titanium alloy lunate prosthesis does not change the wrist joint load transfer mode, which provided data support for the clinical application of the prosthesis.
Humans ; Lunate Bone/surgery* ; Finite Element Analysis ; Titanium ; Wrist Joint/surgery* ; Artificial Limbs ; Range of Motion, Articular ; Biomechanical Phenomena

Objective: To evaluate the long-term efficacy and safety of the implantable ventricular assist system EVAHEART I in clinical use. Methods: Fifteen consecutive patients with end-stage heart failure who received left ventricular assist device therapy in Fuwai Hospital from January 2018 to December 2021 were enrolled in this study, their clinical data were retrospectively analyzed. Cardiac function, liver and kidney function, New York Heart Association (NYHA) classification, 6-minute walk distance and quality of life were evaluated before implantation and at 1, 6, 12, 24 and 36 months after device implantation. Drive cable infection, hemolysis, cerebrovascular events, mechanical failure, abnormally high-power consumption and abnormal pump flow were recorded during follow up. Results: All 15 patients were male, mean average age was (43.0±7.5) years, including 11 cases of dilated cardiomyopathy, 2 cases of ischemic cardiomyopathy, and 2 cases of valvular heart disease. All patients were hemodynamically stable on more than one intravenous vasoactive drugs, and 3 patients were supported by preoperative intra aortic balloon pump (IABP). Compared with before device implantation, left ventricular end-diastolic dimension (LVEDD) was significantly decreased ((80.93±6.69) mm vs. (63.73±6.31) mm, P<0.05), brain natriuretic peptide (BNP), total bilirubin and creatinine were also significantly decreased ((3 544.85±1 723.77) ng/L vs. (770.80±406.39) ng/L; (21.28±10.51) μmol/L vs. (17.39±7.68) μmol/L; (95.82±34.88) μmol/L vs. (77.32±43.81) μmol/L; P<0.05) at 1 week after device implantation. All patients in this group were in NYHA class Ⅳ before implantation, and 9 patients could recover to NYHA class Ⅲ, 3 to class Ⅱ, and 3 to class Ⅰ at 1 month after operation. All patients recovered to class Ⅰ-Ⅱ at 6 months after operation. The 6-minute walk distance, total quality of life and visual analogue scale were significantly increased and improved at 1 month after implantation compared with those before operation (P<0.05). All patients were implanted with EVAHEART I at speeds between 1 700-1 950 rpm, flow rates between 3.2-4.5 L/min, power consumption of 3-9 W. The 1-year, 2-year, and 3-year survival rates were 100%, 87%, and 80%, respectively. Three patients died of multiple organ failure at 412, 610, and 872 d after surgery, respectively. During long-term device carrying, 3 patients developed drive cable infection on 170, 220, and 475 d after surgery, respectively, and were cured by dressing change. One patient underwent heart transplantation at 155 d after surgery due to bacteremia. Three patients developed transient ischemic attack and 1 patient developed hemorrhagic stroke events, all cured without sequelae. Conclusion: EVAHEART I implantable left heart assist system can effectively treat critically ill patients with end-stage heart failure, can be carried for long-term life and significantly improve the survival rate, with clear clinical efficacy.
Humans ; Male ; Adult ; Middle Aged ; Female ; Heart Failure/complications* ; Follow-Up Studies ; Retrospective Studies ; Heart-Assist Devices ; Quality of Life

Objective: To investigate the diagnostic efficiency and clinical application value of an artificial intelligence-assisted diagnosis model based on a three-dimensional convolutional neural network (3D CNN) on echocardiographic videos of patients with hypertensive heart disease, chronic renal failure (CRF) and hypothyroidism with cardiac involvement. Methods: This study is a retrospective study. The patients with hypertensive heart disease, CRF and hypothyroidism with cardiac involvement, who admitted in Henan Provincial People's Hospital from April 2019 to October 2021, were enrolled. Patients were divided into hypertension group, CRF group, and hypothyroidism group. Additionally, a simple random sampling method was used to select control healthy individuals, who underwent physical examination at the same period. The echocardiographic video data of enrolled participants were analyzed. The video data in each group was divided into a training set and an independent testing set in a ratio of 5 to 1. The temporal and spatial characteristics of videos were extracted using an inflated 3D convolutional network (I3D). The artificial intelligence assisted diagnosis model was trained and tested. There was no case overlapped between the training and validation sets. A model was established according to cases or videos based on video data from 3 different views (single apical four chamber (A4C) view, single parasternal left ventricular long-axis (PLAX) view and all views). The statistical analysis of diagnostic performance was completed to calculate sensitivity, specificity and area under the ROC curve (AUC). The time required for the artificial intelligence and ultrasound physicians to process cases was compared. Results: A total of 730 subjects aged (41.9±12.7) years were enrolled, including 362 males (49.6%), and 17 703 videos were collected. There were 212 cases in the hypertensive group, 210 cases in the CRF group, 105 cases in the hypothyroidism group, and 203 cases in the normal control group. The diagnostic performance of the model predicted by cases based on single PLAX view and all views data was excellent: (1) in the hypertensive group, the sensitivity, specificity and AUC of models based on all views data were 97%, 89% and 0.93, respectively, while those of models based on a single PLAX view were 94%, 95%, and 0.94, respectively; (2) in the CRF group, the sensitivity, specificity and AUC of models based on all views data were 97%, 95% and 0.96, respectively, while those of models based on a single PLAX view were 97%, 89%, and 0.93, respectively; (3) in the hypothyroidism group, the sensitivity, specificity and AUC of models based on all views data were 64%, 100% and 0.82, respectively, while those of models based on a single PLAX view were 82%, 89%, and 0.86, respectively. The time required for the 3D CNN model to measure and analyze the echocardiographic videos of each subject was significantly shorter than that for the ultrasound physicians ((23.96±6.65)s vs. (958.25±266.17)s, P<0.001). Conclusions: The artificial intelligence assisted diagnosis model based on 3D CNN can extract the dynamic temporal and spatial characteristics of echocardiographic videos jointly, and quickly and efficiently identify hypertensive heart disease and cardiac changes caused by CRF and hypothyroidism.
Male ; Humans ; Artificial Intelligence ; Retrospective Studies ; Echocardiography/methods* ; Heart Diseases ; Hypertension ; Hypothyroidism

Humans ; Esophagus ; Manometry ; Botulinum Toxins/therapeutic use* ; Prostheses and Implants ; Treatment Outcome ; Larynx, Artificial

Humans ; Artificial Intelligence ; Heart Failure/therapy* ; Electrocardiography

The number of patients with heart failure in China is large, and the proportion of patients with end-stage heart failure continues to increase. The clinical effect of guideline-directed medications therapy for end-stage heart failure is poor. Heart transplantation is the most effective treatment for end-stage heart failure. But it is faced with many limitations such as the shortage of donors. In recent years, the research and development of artificial heart in China has made great progress. Three devices have been approved by the National Medical Products Administration for marketing, and another one is undergoing pre-marketing clinical trial. Since 2017, more than 200 cases of ventricular assist device implantation have been carried out in more than 34 hospitals in China. Among them, 70 patients in Fuwai Hospital, Chinese Academy of Medical Sciences had a 2-year survival rate of 90%. The first patient has survived more than 5 years with the device. More efforts should be put into the training of standardized technical team and quality control. Further research should be carried out in the aspects of pulsatile blood flow pump, fully implanted cable-free device, and improved biomaterial with better blood compatibility.
Humans ; Heart-Assist Devices ; Heart Failure/surgery* ; Heart, Artificial ; Heart Transplantation ; Pulsatile Flow

OBJECTIVE: To use the low-cost anesthesia monitor for realizing anesthesia depth monitoring, effectively assist anesthesiologists in diagnosis and reduce the cost of anesthesia operation. METHODS: Propose a monitoring method of anesthesia depth based on artificial intelligence. The monitoring method is designed based on convolutional neural network (CNN) and long and short-term memory (LSTM) network. The input data of the model include electrocardiogram (ECG) and pulse wave photoplethysmography (PPG) recorded in the anesthesia monitor, as well as heart rate variability (HRV) calculated from ECG, The output of the model is in three states of anesthesia induction, anesthesia maintenance and anesthesia awakening. RESULTS: The accuracy of anesthesia depth monitoring model under transfer learning is 94.1%, which is better than all comparison methods. CONCLUSIONS The accuracy of this study meets the needs of perioperative anesthesia depth monitoring and the study reduces the operation cost.
Artificial Intelligence ; Neural Networks, Computer ; Heart Rate ; Electrocardiography ; Photoplethysmography/methods* ; Anesthesia